CN116720448B - Wind power generation random simulation method, device, equipment and medium - Google Patents
Wind power generation random simulation method, device, equipment and medium Download PDFInfo
- Publication number
- CN116720448B CN116720448B CN202310995610.9A CN202310995610A CN116720448B CN 116720448 B CN116720448 B CN 116720448B CN 202310995610 A CN202310995610 A CN 202310995610A CN 116720448 B CN116720448 B CN 116720448B
- Authority
- CN
- China
- Prior art keywords
- wind power
- distribution function
- power output
- cumulative distribution
- interval
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 97
- 238000004088 simulation Methods 0.000 title claims abstract description 59
- 238000010248 power generation Methods 0.000 title claims abstract description 54
- 238000005315 distribution function Methods 0.000 claims abstract description 140
- 230000001186 cumulative effect Effects 0.000 claims abstract description 128
- 238000005070 sampling Methods 0.000 claims abstract description 39
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 230000006870 function Effects 0.000 claims description 55
- 238000012216 screening Methods 0.000 claims description 29
- 230000015654 memory Effects 0.000 claims description 27
- 238000013507 mapping Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 description 7
- 241001123248 Arma Species 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003064 k means clustering Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 101000614599 Homo sapiens Jerky protein homolog Proteins 0.000 description 1
- 102100040507 Jerky protein homolog Human genes 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Wind Motors (AREA)
Abstract
The invention relates to the technical field of wind power generation, and discloses a wind power generation random simulation method, a device, equipment and a medium, wherein the method comprises the following steps: acquiring a deviation data set; fitting the data in the deviation data set, and carrying out integral calculation on the fitting result to obtain a first cumulative distribution function; determining a corresponding target output interval when the first accumulated distribution function value takes a preset risk preference value; reconstructing a cumulative distribution function based on a preset reconstruction rule and a target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function; sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the concentrated wind power output scene of the wind power plant. By the method, the wind power generation random simulation method considering influence of risk preference is realized, and actual requirements of users are met.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a wind power generation random simulation method, device, equipment and medium.
Background
With the increasing of the clean energy ratio in the power grid, the influence of the strong intermittence and fluctuation on the power system is increasingly prominent. In researching scheduling and running problems of a wind power access system, modeling analysis needs to be carried out on inherent randomness of wind power, and multi-scene simulation is one of the most common random modeling analysis methods, the principle of which is that randomness of wind power is represented through a plurality of typical scene simulations obeying specific probability statistical characteristics, and the basic idea of the method is derived from Monte Carlo theory. Aiming at robust optimal scheduling and related problems of a wind power access system, sometimes the risk attitudes of scheduling decision makers are required to be fused, and a risk preference wind power random simulation method considering decision makers is constructed, so that the method becomes a real demand. The existing wind power random simulation technology can not quantify the risk attitude and influence of a decision maker, and cannot realize wind power generation uncertainty characterization and simulation under the action of risk preference.
Disclosure of Invention
In view of the above, the present invention provides a wind power generation random simulation method, device, apparatus and medium, so as to solve the problem that risk preference cannot be considered in the wind power generation random simulation process.
In a first aspect, the present invention provides a wind power generation random simulation method, the method comprising:
acquiring a deviation data set, wherein data in the deviation data set are used for indicating the deviation between the wind power output actual value and the wind power output predicted value at the same moment; fitting the data in the deviation data set, and performing integral calculation on the fitting result to obtain a first cumulative distribution function; determining a corresponding target output interval when the first accumulated distribution function value takes a preset risk preference value; reconstructing a cumulative distribution function based on a preset reconstruction rule and a target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function; sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the concentrated wind power output scene of the wind power plant.
According to the wind power generation random simulation method provided by the embodiment, after the first cumulative distribution function is obtained, the corresponding target output interval is determined by combining the preset risk preference value. And reconstructing a cumulative distribution function through a preset reconstruction rule and a target output interval to obtain a second cumulative distribution function, and sampling the second cumulative distribution function at different moments to generate a wind power output scene set meeting risk preference, thereby realizing simulation operation on wind power randomness. According to the wind power generation random simulation method based on the risk preference effect, the wind power generation random simulation method based on the risk preference effect is achieved, and the requirements of users with different risk preferences are met. Therefore, the user can perform random simulation according to the acceptable risk, and further the influence of the subjectivity of the user on the wind power generation random simulation is improved.
In an alternative embodiment, acquiring the deviation dataset comprises:
acquiring a first historical data set corresponding to a first historical stage and a second historical data set corresponding to a second historical stage; inputting the first historical data set into a pre-constructed prediction model to obtain a prediction data set corresponding to the second historical stage; a bias data set is generated based on the second historical data set and the prediction data set.
According to the method, the first historical data set is predicted through the prediction model, so that accuracy of a prediction result is improved, and the speed of prediction is also improved.
In an alternative embodiment, the pre-constructed predictive model is an autoregressive moving average model.
In the embodiment, the autoregressive moving average model is adopted to predict the first historical data set, and the model has a very simple structure, and only endogenous variables are needed without other exogenous variables, so that the model prediction efficiency is improved.
In an alternative embodiment, fitting the data in the deviation dataset and performing integral calculation on the fitting result to obtain a first cumulative distribution function, including:
fitting the data in the deviation data set by adopting a kernel density estimation method to obtain a probability density function; and integrating the probability density function to obtain a first cumulative distribution function.
In the embodiment, a kernel density estimation method is adopted to fit data in a deviation data set, so that a probability density function is obtained. According to the method, only one parameter of the window width is required to be set, and the optimal window width is determined through an optimal window width selection formula, so that probability density estimation is more accurate.
In an alternative embodiment, determining the corresponding target output interval when the first cumulative distribution function value takes the preset risk preference value includes:
determining a corresponding wind power output interval when the first accumulated distribution function value takes a preset risk preference value; when one wind power output interval exists, determining the wind power output interval as a target output interval; when a plurality of wind power output sections exist, a target output section is screened out from the plurality of wind power output sections according to a preset screening rule.
In an alternative embodiment, when there are a plurality of wind power output intervals, according to a preset screening rule, screening a target output interval from the plurality of wind power output intervals includes:
calculating the interval length corresponding to each wind power output interval; and screening out the minimum value from the interval length, and determining the wind power output interval corresponding to the minimum value as a target output interval.
In an alternative embodiment, reconstructing the cumulative distribution function based on a preset reconstruction rule and a target output interval, and determining the reconstructed cumulative distribution function as the second cumulative distribution function includes:
dividing the target output interval into a plurality of subintervals in equal proportion; acquiring first function values respectively corresponding to the endpoints of each subinterval in a first cumulative distribution function; mapping the first function value into a second function value based on a preset mapping relation; a second cumulative distribution function is generated based on each subinterval endpoint and a second function value corresponding to each subinterval endpoint.
According to the method, the first cumulative distribution function corresponding to the target output interval is extracted and reconstructed, so that the distribution rule of the original data in the probability space is maintained to a certain extent, the characteristics of the original probability distribution are reserved, and the consistency of the data statistical characteristics is maintained.
In an alternative embodiment, sampling the second cumulative distribution function at different moments to obtain a wind power output scenario set meeting the risk preference includes:
sampling the second cumulative distribution function at different moments by using a Latin hypercube sampling method to generate a wind power output scene corresponding to each moment; and arranging the wind power output scene sets according to the time sequence order of the time, and forming the wind power output scene sets meeting the risk preference.
According to the wind power generation random simulation method, scene generation is performed by using the Latin hypercube sampling method, and the method is a layered sampling method, so that samples can be uniformly extracted, extraction values are prevented from being concentrated in a certain area, and the usability of the samples is further improved.
In an alternative embodiment, after obtaining the wind power output scenario set meeting the risk preference, before simulating the wind power randomness based on the wind power output scenario, the method further comprises:
and (5) cutting down the wind power output scene set.
In the wind power generation random simulation method provided in this embodiment, in order to ensure the comprehensiveness of sample distribution, the number of samples generally extracted is set to be relatively large, so that the calculation burden of the scheduling model is greatly increased. Therefore, the present embodiment cuts down on the scene after generating the set of wind power output scenes. By combining similar scenes in the scenes, the finally obtained optimal scene set can describe the randomness of wind power output and ensure that no great calculation load is brought to the scheduling model.
In a second aspect, the present invention provides a wind power generation random simulation device, the device comprising:
The acquisition module is used for acquiring a deviation data set, wherein the data in the deviation data set is used for indicating the deviation between the wind power output actual value and the wind power output predicted value at the same moment; the processing module is used for fitting the data in the deviation data set, and carrying out integral calculation on the fitting result to obtain a first cumulative distribution function; the determining module is used for determining a corresponding target output interval when the first accumulated distribution function value takes a preset risk preference value; the reconstruction module is used for reconstructing a cumulative distribution function based on a preset reconstruction rule and a target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function; the sampling module is used for sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the concentrated wind power output scene of the wind power plant.
In an alternative embodiment, the obtaining module includes:
the acquisition sub-module is used for acquiring a first historical data set corresponding to the first historical stage and a second historical data set corresponding to the second historical stage; the input sub-module is used for inputting the first historical data set into a pre-constructed prediction model to obtain a prediction data set corresponding to the second historical stage; and a generation sub-module for generating a deviation dataset based on the second historical dataset and the prediction dataset.
In an alternative embodiment, the predictive model pre-built in the input sub-module is an autoregressive moving average model.
In an alternative embodiment, a processing module includes:
the fitting sub-module is used for fitting the data in the deviation data set by adopting a kernel density estimation method to obtain a probability density function; and the operation submodule is used for integrating the probability density function to obtain a first cumulative distribution function.
In a third aspect, the present invention provides a computer device comprising: the wind power generation random simulation method comprises the steps of storing a wind power generation random simulation program, wherein the wind power generation random simulation program comprises a memory and a processor, the memory is in communication connection with the processor, the memory stores computer instructions, and the processor executes the computer instructions, so that the wind power generation random simulation method of the first aspect or any corresponding implementation mode is executed.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions for causing a computer to execute the wind power generation random simulation method of the first aspect or any of the embodiments corresponding thereto.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a wind power generation random simulation method according to an embodiment of the invention;
FIG. 2 is a flow chart of another wind power generation random simulation method according to an embodiment of the invention;
FIG. 3 is a flow chart of yet another wind power generation random simulation method according to an embodiment of the present invention;
FIG. 4 is a flow chart of a random simulation method of wind power generation according to an embodiment of the invention;
FIG. 5 is a block diagram of a wind power generation random simulation device according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The wind power generation random simulation method in the related art cannot be combined with risk preference of users, so that user requirements cannot be met. The embodiment of the invention provides a wind power generation random simulation method, which is used for determining a wind power output interval capable of reaching a risk preference value through presetting the risk preference value. After the cumulative distribution function corresponding to the wind power output section is reconstructed, sampling the reconstructed cumulative distribution function at different moments, so that a wind power output scene set meeting the risk preference is obtained, and the randomness of wind power output is simulated through a multi-scene method, so that the effect of meeting the user requirement is achieved.
According to an embodiment of the present invention, there is provided a wind power generation random simulation method embodiment, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order different from that herein.
In this embodiment, a wind power generation random simulation method is provided, which may be used for a processor, and fig. 1 is a flowchart of a wind power generation random simulation method according to an embodiment of the present invention, as shown in fig. 1, where the flowchart includes the following steps:
step S101, a deviation dataset is acquired.
Specifically, the data in the deviation data set is used to indicate the deviation between the actual value of the wind power output and the predicted value of the wind power output at the same time, and the deviation is also expressed as a prediction error.
Step S102, fitting the data in the deviation data set, and carrying out integral calculation on the fitting result to obtain a first cumulative distribution function.
Specifically, after fitting the data in the deviation data set, a probability density function corresponding to the deviation is obtained, and a cumulative distribution function (i.e., a first cumulative distribution function) is obtained by integrating the probability density function.
Step S103, determining a corresponding target output interval when the first accumulated distribution function value takes a preset risk preference value.
Specifically, the risk preference value is a probability value set according to the risk preference of the user, and is used for representing the acceptable prediction error degree of the user, and the value range of the risk preference value is between 0 and 1, and is more conservative when the value is closer to 1. When a preset risk preference value, namely a preset risk preference value, is received or acquired, the preset risk preference value is substituted into the first cumulative distribution function, so that a corresponding target processing interval is obtained.
Step S104, reconstructing a cumulative distribution function based on a preset reconstruction rule and a target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function.
Specifically, the preset reconstruction rule is not limited herein, and any reconstruction method may be used. For example, the preset reconstruction rule may be to re-fit the deviation value based on the target output interval, and perform integral operation on the probability density function formed after the fitting, so as to obtain a second cumulative distribution function.
Step S105, sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the concentrated wind power output scene of the wind power plant.
Specifically, after the wind power output scene set is obtained, the randomness of wind power is simulated by adopting a multi-scene method. The multi-scenario approach is well established in the art and will not be described in detail herein.
According to the wind power generation random simulation method provided by the embodiment, after the first cumulative distribution function is obtained, the corresponding target output interval is determined by combining the preset risk preference value. And reconstructing a cumulative distribution function through a preset reconstruction rule and a target output interval to obtain a second cumulative distribution function, and sampling the second cumulative distribution function at different moments to generate a wind power output scene set meeting risk preference, thereby realizing simulation operation on wind power randomness. According to the wind power generation random simulation method based on the risk preference effect, the wind power generation random simulation method based on the risk preference effect is achieved, and the requirements of users with different risk preferences are met. Therefore, the user can perform random simulation according to the acceptable risk, and further the influence of the subjectivity of the user on the wind power generation random simulation is improved.
In this embodiment, a wind power generation random simulation method is provided, which may be used for a processor, and fig. 2 is a flowchart of the wind power generation random simulation method according to an embodiment of the present invention, as shown in fig. 2, where the flowchart includes the following steps:
Step S201, a deviation dataset is acquired.
Specifically, the step S201 includes:
in step S2011, a first historical data set corresponding to the first historical stage and a second historical data set corresponding to the second historical stage are obtained.
Specifically, the first history phase and the second history phase are two time periods adjacent in time.
Specifically, the historical data set is a set of historical wind power output data collected from the target wind farm. The collection mode of the historical wind power output data can be that wind power output data of a wind power machine of a target wind power plant in a certain historical time period is collected at fixed data sampling intervals.
Illustratively, the first historical stage is 2022, 1-30 years, 2022, 6-30 years, and the second historical stage is 2022, 7-1-31 years, 2022, 7-31 years. The first historical data set is actual output data corresponding to a certain fan of the target wind power plant in a first historical stage, wherein the actual output data are acquired at data sampling intervals of 1 h. The second historical data set is actual output data corresponding to a certain fan of the target wind power plant in a second historical stage, wherein the actual output data are acquired at data sampling intervals of 1 h.
Step S2012, the first historical data set is input into a pre-constructed prediction model to obtain a prediction data set corresponding to the second historical stage.
Specifically, the selection of the prediction model is not particularly limited herein, and those skilled in the art can select the prediction model according to actual needs. The pre-constructed prediction model can be an autoregressive model (Autoregressive model, abbreviated as AR model), a moving average model (moving average model, abbreviated as MA model), an autoregressive moving average model (Auto-Regressive Moving Average Model, abbreviated as ARMA model), a Prophet model, and the like. Wherein the Prophet model is a large-scale event sequence prediction model.
Illustratively, the ARMA model is employed in this embodiment to predict the first historical dataset. The ARMA model is embodied by:
；
wherein,is->Wind power output data of moment,/>Is a random variable +.>For the running average parameter +.>For autoregressive parameters, < >>Is->Order autoregressive process,>is->A step-wise moving average process.
It should be noted that, in modeling, to obtain a smooth random sequence (i.e., in the ARMA model) The random variables need to be smoothed. Specifically, the data can be stabilized by adopting a differential method, and meanwhile, in order to ensure the operation precision, the data after the stabilization is subjected to standardized processing.
Wherein, the difference formula is:
；
wherein,for differential order>Is the jerky sequence data.
The standardized processing formula is:
；
wherein,for the sequence->Mean estimate of (i.e. sample mean,)>Is->Mean square error estimate of (c).
After the above processing, the order of the model, i.e. the autoregressive order, needs to be further determinedSliding average order->. The model order can be determined by autocorrelation and partial autocorrelation analysis on time series samples, using autocorrelation and partial autocorrelation curves, and then selecting a number of models of different orders for analysis, and ranking the models according to a minimum information criterion (AIC criterion). This process is prior art and will not be described in detail here.
After the model order is determined, parameter estimation is also performed on the model. For example, a least squares estimation method may be used to estimate parameters of the model, and finally obtain a prediction model.
Step S2013, generating a bias data set based on the second historical data set and the prediction data set.
Specifically, the deviation data in the deviation data set is the difference between the history data and the prediction data at the same time. The historical data belongs to the second historical data set and the predicted data belongs to the predicted data set.
Step S202, fitting the data in the deviation data set, and performing integral calculation on the fitting result to obtain a first cumulative distribution function.
Specifically, step S202 includes:
in step S2021, a kernel density estimation method is used to fit the data in the deviation dataset, so as to obtain a probability density function.
Illustratively, still taking the embodiment corresponding to step S2011 as an example, the deviation dataset includes predicted deviations corresponding to each hour of each day in the second history period. And screening out the predicted deviation corresponding to the same time of each day in the second historical stage from the deviation data set, taking the predicted deviation as a random sample of wind power output, and fitting the random sample to obtain a probability density function. For example, the deviation dataset is the predicted deviation for each hour of each of the 7 months of 2022. And (3) screening deviation data corresponding to the ith hour of each day in 7 months of 2022 from all the deviations, taking the data as random samples, and fitting the data to obtain a probability density function corresponding to the ith hour. Wherein i is any one hour of 1 to 24. Therefore, each hour corresponds to a probability density function, and accordingly, the probability density functions corresponding to each hour are integrated in the subsequent integral calculation of the probability density functions, and similarly, the target output data and the first cumulative distribution function corresponding to each hour are reconstructed in the subsequent reconstruction operation.
Probability density functionThe following is shown:
；
wherein,sample volume,/->Is window width->Is a kernel function.
Wherein the window widthAnd therefore, the window width needs to be determined first. The optimal window width selection formula is as follows:
；
the minimum point of the function is taken as the estimated value of the optimal window width as the overall empirical distribution function.
When the kernel function takes a gaussian kernel function, the probability density function is:
；
in step S2022, the probability density function is integrated to obtain a first cumulative distribution function.
；
For the first cumulative distribution function +.>As a function of probability density.
Step S203, determining a corresponding target output interval when the first cumulative distribution function value takes the preset risk preference value. Please refer to step S103 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S204, reconstructing a cumulative distribution function based on a preset reconstruction rule and a target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function. Please refer to step S104 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S205, sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the concentrated wind power output scene of the wind power plant. Please refer to step S105 in the embodiment shown in fig. 1 in detail, which is not described herein.
According to the wind power generation random simulation method provided by the embodiment, the data in the deviation data set is fitted by adopting a nuclear density estimation method, so that a probability density function is obtained. According to the method, only one parameter of the window width is required to be set, and the optimal window width is determined through an optimal window width selection formula, so that probability density estimation is more accurate.
In this embodiment, a wind power generation random simulation method is provided, which may be used for a processor, and fig. 3 is a flowchart of the wind power generation random simulation method according to an embodiment of the present invention, as shown in fig. 3, where the flowchart includes the following steps:
step S301, a deviation dataset is acquired. Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S302, fitting the data in the deviation data set, and performing integral calculation on the fitting result to obtain a first cumulative distribution function. Please refer to step S102 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S303, determining a corresponding target output interval when the first cumulative distribution function value takes the preset risk preference value.
Specifically, step S303 includes:
step S3031, a corresponding wind power output interval when the first accumulated distribution function value takes a preset risk preference value is determined.
Specifically, the wind power output interval that enables the first cumulative distribution function value to be equal to the preset risk preference value may be one or more.
Step S3032, when one wind power output interval exists, determining the wind power output interval as a target output interval.
Step S3033, when a plurality of wind power output sections exist, screening out target output sections from the plurality of wind power output sections according to a preset screening rule.
Specifically, the preset screening rule may be to select a wind power output section with the smallest selection length from a plurality of wind power output sections. The preset screening rule may also be a plurality of wind power output intervals symmetric about the vertical axis selected from the wind power processing intervals. Specifically, the wind power output section symmetrical about the vertical axis is a wind power output section corresponding to the wind power output section when the integral value is the risk preference value, and the integral value is obtained by equally taking the integral value along the two sides of the horizontal axis with the origin as the center. The preset screening rules are not particularly limited herein, and may be selected by those skilled in the art according to actual application scenarios.
In some alternative embodiments, step S3031 includes:
and a1, calculating the interval length corresponding to each wind power output interval.
Specifically, the interval length is the difference between the two ends of the interval. Such as the closed interval [2,8], the interval length of which is 6.
And a2, screening out the minimum value from the interval length, and determining the wind power output interval corresponding to the minimum value as a target output interval.
For example, there are 4 wind power output intervals corresponding to the first cumulative distribution function taking the preset risk preference value, which are respectively [2,8], [3,7], [4,5], [5, 17]. The section length of the wind power output section was determined according to the method described in step a1 and was 6,4,1 and 12, respectively. And selecting a minimum length value, namely 1, from the interval length values, and determining a wind power output interval [4,5] corresponding to the 1 as a target output interval.
Step S304, reconstructing a cumulative distribution function based on a preset reconstruction rule and a target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function.
Specifically, step S304 includes:
in step S3041, the target output interval is equally divided into a plurality of sub-intervals.
Illustratively, the target output interval is%，/>) Will ()>，/>) Equally dividing into n+1 subintervals, wherein the corresponding abscissa points after dividing are respectively (/ -)>，/>，/>，…，/>，/>）。
Step S3042, obtaining first function values corresponding to the sub-interval endpoints in the first cumulative distribution function.
Illustratively, a function value (i.e., a first function value) of each subinterval endpoint in a first cumulative distribution function within a target output interval is obtained. Respectively is ，/>，/>，…，/>，/>。
Step S3043, mapping the first function value to the second function value based on the preset mapping relation.
Illustratively, according to a preset mapping relationship，/>，/>，…，/>，Mapping to a range of 0 to 1. The mapping is an equal scaling ordinate.
Illustratively, to @，/>) For example, the mapped coordinates are (+.>，/>). The preset mapping relation is as follows:
；
i.e.
；
Step S3044, generating a second cumulative distribution function based on each subinterval endpoint and the second function value corresponding to each subinterval endpoint.
Illustratively, will，/>），（/>，/>），（/>，/>），…，（/>，/>），（，/>) The isocenters are connected to generate a second cumulative distribution function.
The reconstruction of the cumulative distribution function is equivalent to the removal of the part except the target output interval corresponding to the preset risk bias value, and the removal of the target output interval corresponding to the preset risk bias value，/>) As a focus of attention. Since the probability corresponding to the cumulative distribution function is less than 1 due to the elimination of the portion other than the target output interval, it is necessary to map the probability value corresponding to the target output interval to the range of 0 to 1 by reconstructing the cumulative distribution function.
Step S305, sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the concentrated wind power output scene of the wind power plant. Please refer to step S105 in the embodiment shown in fig. 1 in detail, which is not described herein.
According to the wind power generation random simulation method, the risk preference value is set, so that the target output interval corresponding to the risk preference value is determined, and the first cumulative distribution function corresponding to the target output interval is extracted and reconstructed, so that the distribution rule of the original data in the probability space is maintained to a certain extent, and the consistency of the data statistics characteristics is also maintained.
In this embodiment, a wind power generation random simulation method is provided, which may be used for a processor, and fig. 4 is a flowchart of the wind power generation random simulation method according to an embodiment of the present invention, as shown in fig. 4, where the flowchart includes the following steps:
in step S401, a deviation dataset is acquired. Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S402, fitting the data in the deviation data set, and performing integral calculation on the fitting result to obtain a first cumulative distribution function. Please refer to step S102 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S403, determining a target output interval corresponding to the first cumulative distribution function value when the first cumulative distribution function value takes the preset risk preference value. Please refer to step S103 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S404, reconstructing a cumulative distribution function based on a preset reconstruction rule and a target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function. Please refer to step S104 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S405, sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the concentrated wind power output scene of the wind power plant.
Specifically, step S405 includes:
and step S4051, sampling the second cumulative distribution function at different moments by using a Latin hypercube sampling method, and generating a wind power output scene corresponding to each moment.
Each time instance will illustratively correspond to a second cumulative distribution function. And sampling the second cumulative distribution function corresponding to each moment to obtain the wind power output scene corresponding to each moment.
Still taking the embodiment in step S2021 as an example, the sampling process thereof is described. The second cumulative distribution function corresponding to the 3 rd hour is sampled to obtain n prediction deviations, namely p1, p2, … and pn. And respectively obtaining a predicted output value corresponding to the moment of each predicted deviation, and obtaining output data, namely q1, q2, … and qn, based on the predicted output value and the predicted deviation data. Based on q1, q2, …, qn, a wind power output scene corresponding to the 3 rd hour is generated.
Step S4052, arranging the wind power output scene sets according to the time sequence order of the time, and forming the wind power output scene sets meeting the risk preference.
Illustratively, in step S4051, a wind power output scenario corresponding to each of 24 hours is calculated. And sequencing the 24 wind power output scenes according to the time sequence corresponding to the time, and forming a wind power output scene set by the sequenced wind power processing scenes.
According to the wind power generation random simulation method, scene generation is performed by using the Latin hypercube sampling method, and the method is a layered sampling method, so that samples can be uniformly extracted, extraction values are prevented from being concentrated in a certain area, and the usability of the samples is further improved.
In some alternative embodiments, after step S4051, before step S4052, step S405 further includes:
and (5) cutting down the wind power output scene set.
Illustratively, 24 scenes in the wind power output scene set are cut down to 10 scenes. The reduction method comprises, but is not limited to, reduction by a K-means clustering method and a K-means clustering algorithm. The cutting mode is not particularly limited herein, and a person skilled in the art can select the cutting mode according to the actual application scenario.
In the wind power generation random simulation method provided in this embodiment, in order to ensure the comprehensiveness of sample distribution, the number of samples generally extracted is set to be relatively large, so that the calculation burden of the scheduling model is greatly increased. Therefore, the present embodiment cuts down on the scene after generating the set of wind power output scenes. By combining similar scenes in the scenes, the finally obtained optimal scene set can describe the randomness of wind power output and ensure that no great calculation load is brought to the scheduling model.
As a preferred embodiment of the embodiments of the present invention, the following describes the present invention in detail in connection with a practical application scenario.
Firstly, a first historical data set corresponding to a first historical stage and a second historical data set corresponding to a second historical stage are obtained, the first historical data set is input into an ARMA model, and a prediction data set corresponding to the second historical stage is predicted. A bias dataset is calculated from the prediction dataset and the second historical dataset. After the deviation data set is obtained, fitting the data in the deviation data set by adopting a kernel density estimation method to obtain a probability density function corresponding to the deviation, and performing integral operation on the probability density function to obtain a first cumulative distribution function.
And secondly, taking a wind power output section when the first cumulative distribution function value is equal to a preset risk preference value, selecting a wind power output section with the minimum section length from all the wind power output sections, and taking the section as a target output section.
And reconstructing a part corresponding to the target output interval in the first cumulative distribution function, wherein the reconstruction mode is to map the first cumulative distribution function value corresponding to the abscissa included in the target output interval in the first cumulative distribution function to a range from 0 to 1 respectively to obtain a second cumulative distribution function value corresponding to each abscissa, and constructing the second cumulative distribution function based on the second cumulative distribution function value corresponding to each abscissa, namely each abscissa, in the target output interval.
And finally, sampling the second cumulative distribution function at different moments by using a Latin hypercube sampling method to generate a wind power output scene corresponding to each moment, and forming a wind power output scene set by the wind power output scenes corresponding to all the moments. And reducing the wind power output scene set through a K-means clustering algorithm to obtain a wind power output scene set which meets the reduction of risk preference, and simulating wind power randomness through a multi-scene method.
In this embodiment, a wind power generation random simulation device is further provided, and the device is used to implement the foregoing embodiments and preferred embodiments, and will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The present embodiment provides a wind power generation random simulation device, as shown in fig. 5, including:
the obtaining module 501 is configured to obtain a deviation data set, where data in the deviation data set is used to indicate a deviation between a real wind power output value and a predicted wind power output value at the same time.
The processing module 502 is configured to fit the data in the deviation data set, and perform integral calculation on the fitting result to obtain a first cumulative distribution function.
A determining module 503, configured to determine a target output interval corresponding to the first cumulative distribution function value when the first cumulative distribution function value takes a preset risk preference value.
A reconstruction module 504, configured to reconstruct a cumulative distribution function based on a preset reconstruction rule and a target output interval, and determine the reconstructed cumulative distribution function as a second cumulative distribution function.
The sampling module 505 is configured to sample the second cumulative distribution function at different moments to obtain a wind power output scenario set meeting the risk preference, and simulate wind power randomness based on the concentrated wind power output scenario of the wind power plant.
In some alternative embodiments, the acquisition module 501 includes:
and the acquisition sub-module is used for acquiring a first historical data set corresponding to the first historical stage and a second historical data set corresponding to the second historical stage.
And the input sub-module is used for inputting the first historical data set into a pre-constructed prediction model to obtain a prediction data set corresponding to the second historical stage.
And a generation sub-module for generating a deviation dataset based on the second historical dataset and the prediction dataset.
In some alternative embodiments, the predictive model pre-built in the input sub-module is an autoregressive moving average model.
In some alternative embodiments, the processing module 502 includes:
and the fitting sub-module is used for fitting the data in the deviation data set by adopting a kernel density estimation method to obtain a probability density function.
And the operation submodule is used for integrating the probability density function to obtain a first cumulative distribution function.
In some alternative embodiments, the determining module 503 includes:
the first determining submodule is used for determining a wind power output interval corresponding to the first accumulated distribution function value when the first accumulated distribution function value takes a preset risk preference value.
And the second determining submodule is used for determining the wind power output interval as a target output interval when one wind power output interval exists.
And the screening sub-module is used for screening out a target output interval from the plurality of wind power output intervals according to a preset screening rule when the plurality of wind power output intervals exist.
In some alternative embodiments, the screening submodule includes:
and the calculating unit is used for calculating the interval length corresponding to each wind power output interval.
And the screening calculation unit is used for screening the minimum value from the interval length and determining the wind power output interval corresponding to the minimum value as a target output interval.
In some alternative embodiments, the reconstruction module 504 includes:
and the dividing sub-module is used for dividing the target output interval into a plurality of sub-intervals in equal proportion.
And the acquisition sub-module is used for acquiring first function values respectively corresponding to the endpoints of each sub-interval in the first cumulative distribution function.
And the mapping sub-module is used for mapping the first function value into a second function value based on a preset mapping relation.
And the generation submodule is used for generating a second cumulative distribution function based on each subinterval endpoint and a second function value corresponding to each subinterval endpoint.
In some alternative embodiments, the sampling module 505 includes:
and the sampling sub-module is used for sampling the second cumulative distribution function at different moments by using a Latin hypercube sampling method, and generating a wind power output scene corresponding to each moment.
And the arrangement sub-module is used for arranging the wind power output scene sets according to the time sequence order of the time and forming the wind power output scene sets meeting the risk preference.
In some alternative embodiments, after the sampling sub-module, before the arranging sub-module, further comprising:
and the reduction submodule is used for reducing the wind power output scene set.
Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.
The wind power random simulation device in this embodiment is presented in the form of functional units, where the units refer to ASIC (Application Specific Integrated Circuit ) circuits, processors and memories executing one or more software or fixed programs, and/or other devices that can provide the above described functions.
The embodiment of the invention also provides computer equipment, which is provided with the wind power generation random simulation device shown in the figure 5.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 6, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 6.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform a method for implementing the embodiments described above.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device also includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (12)
1. A wind power generation random simulation method, the method comprising:
acquiring a deviation data set, wherein data in the deviation data set are used for indicating the deviation between the wind power output actual value and the wind power output predicted value at the same moment;
fitting the data in the deviation data set, and performing integral calculation on the fitting result to obtain a first cumulative distribution function;
determining a corresponding target output interval when the first accumulated distribution function value takes a preset risk preference value;
reconstructing a cumulative distribution function based on a preset reconstruction rule and the target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function;
sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the wind power output scene in the wind power output scene set;
Wherein determining the target output interval corresponding to the first cumulative distribution function value when the first cumulative distribution function value takes the preset risk preference value comprises:
determining a corresponding wind power output interval when the first accumulated distribution function value takes a preset risk preference value;
when one wind power output interval exists, determining the wind power output interval as the target output interval;
when a plurality of wind power output intervals exist, screening the target output interval from the plurality of wind power output intervals according to a preset screening rule;
when there are a plurality of wind power output intervals, according to a preset screening rule, screening the target output interval from the plurality of wind power output intervals, including:
calculating the interval length corresponding to each wind power output interval;
screening a minimum value from the interval length, and determining a wind power output interval corresponding to the minimum value as the target output interval;
reconstructing a cumulative distribution function based on a preset reconstruction rule and the target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function, wherein the method comprises the following steps:
dividing the target output interval into a plurality of subintervals in equal proportion;
Acquiring first function values respectively corresponding to all subinterval endpoints in the first cumulative distribution function;
mapping the first function value into a second function value based on a preset mapping relation;
and generating the second cumulative distribution function based on the sub-interval endpoints and the second function values corresponding to the sub-interval endpoints.
2. The method of claim 1, wherein the acquiring the deviation dataset comprises:
acquiring a first historical data set corresponding to a first historical stage and a second historical data set corresponding to a second historical stage;
inputting the first historical data set into a pre-constructed prediction model to obtain a prediction data set corresponding to a second historical stage;
the bias data set is generated based on the second historical data set and the prediction data set.
3. The method of claim 2, wherein the pre-constructed predictive model is an autoregressive moving average model.
4. A method according to any one of claims 1 to 3, wherein said fitting the data in the deviation dataset and integrating the fit results to obtain a first cumulative distribution function comprises:
Fitting the data in the deviation data set by adopting a kernel density estimation method to obtain a probability density function;
and integrating the probability density function to obtain the first cumulative distribution function.
5. The method of claim 1, wherein sampling the second cumulative distribution function at different times results in a set of wind power output scenarios meeting risk preferences, comprising:
sampling the second cumulative distribution function at different moments by using a Latin hypercube sampling method to generate a wind power output scene corresponding to each moment;
and arranging the wind power output scene sets according to the time sequence order of the time, and forming the wind power output scene set meeting the risk preference.
6. The method of claim 5, wherein after the obtaining the set of wind power output scenarios meeting risk preferences, before the simulating wind power randomness based on the wind power output scenarios, further comprising:
and cutting down the wind power output scene set.
7. A wind power generation random simulation device, the device comprising:
the acquisition module is used for acquiring a deviation data set, wherein the data in the deviation data set is used for indicating the deviation between the wind power output actual value and the wind power output predicted value at the same moment;
The processing module is used for fitting the data in the deviation data set, and carrying out integral calculation on the fitting result to obtain a first cumulative distribution function;
the determining module is used for determining a corresponding target output interval when the first accumulated distribution function value takes a preset risk preference value;
the reconstruction module is used for reconstructing a cumulative distribution function based on a preset reconstruction rule and the target output interval, and determining the reconstructed cumulative distribution function as a second cumulative distribution function;
the sampling module is used for sampling the second cumulative distribution function at different moments to obtain a wind power output scene set meeting risk preference, and simulating wind power randomness based on the wind power output scene in the wind power output scene set;
the determining module comprises:
the first determining submodule is used for determining a wind power output interval corresponding to the first cumulative distribution function value when the first cumulative distribution function value takes a preset risk preference value;
the second determining submodule is used for determining the wind power output interval as a target output interval when one wind power output interval exists;
the screening submodule is used for screening a target output interval from the plurality of wind power output intervals according to a preset screening rule when the plurality of wind power output intervals exist;
The screening submodule comprises:
the calculating unit is used for calculating the interval length corresponding to each wind power output interval;
the screening calculation unit is used for screening the minimum value from the interval length and determining the wind power output interval corresponding to the minimum value as a target output interval;
the reconstruction module comprises:
dividing the target output interval into a plurality of subintervals in equal proportion;
the acquisition sub-module is used for acquiring first function values respectively corresponding to the endpoints of each sub-interval in the first cumulative distribution function;
the mapping sub-module is used for mapping the first function value into a second function value based on a preset mapping relation;
and the generation submodule is used for generating a second cumulative distribution function based on each subinterval endpoint and a second function value corresponding to each subinterval endpoint.
8. The apparatus of claim 7, wherein the acquisition module comprises:
the acquisition sub-module is used for acquiring a first historical data set corresponding to the first historical stage and a second historical data set corresponding to the second historical stage;
the input sub-module is used for inputting the first historical data set into a pre-constructed prediction model to obtain a prediction data set corresponding to a second historical stage;
A generation sub-module for generating the deviation dataset based on the second historical dataset and the prediction dataset.
9. The apparatus of claim 8, wherein the predictive model pre-built in the input sub-module is an autoregressive moving average model.
10. The apparatus according to any one of claims 7 to 9, wherein the processing module comprises:
the fitting sub-module is used for fitting the data in the deviation data set by adopting a kernel density estimation method to obtain a probability density function;
and the operation submodule is used for integrating the probability density function to obtain the first cumulative distribution function.
11. A computer device, comprising:
a memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the wind power generation random simulation method of any one of claims 1 to 6.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon computer instructions for causing a computer to execute the wind power generation random simulation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310995610.9A CN116720448B (en) | 2023-08-09 | 2023-08-09 | Wind power generation random simulation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310995610.9A CN116720448B (en) | 2023-08-09 | 2023-08-09 | Wind power generation random simulation method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116720448A CN116720448A (en) | 2023-09-08 |
| CN116720448B true CN116720448B (en) | 2024-01-26 |
Family
ID=87873790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310995610.9A Active CN116720448B (en) | 2023-08-09 | 2023-08-09 | Wind power generation random simulation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116720448B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117522012A (en) * | 2023-11-02 | 2024-02-06 | 长江水利委员会水文局 | Runoff scene generation method based on seasonal period characteristics |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004086896A (en) * | 2002-08-06 | 2004-03-18 | Fuji Electric Holdings Co Ltd | Method and system for constructing adaptive prediction model |
| CN103259285A (en) * | 2013-05-03 | 2013-08-21 | 国家电网公司 | Method for optimizing short running of electric power system comprising large-scale wind power |
| CN103955779A (en) * | 2014-05-23 | 2014-07-30 | 武汉大学 | Wind power climbing event probability scene prediction method |
| CN107944640A (en) * | 2017-12-18 | 2018-04-20 | 国网山东省电力公司经济技术研究院 | A kind of regenerative resource portfolio optimization optimisation technique method and device |
| CN109816149A (en) * | 2018-12-28 | 2019-05-28 | 中国电力科学研究院有限公司 | A kind of wind power plant is contributed scene generating method and device at random |
| CN110807554A (en) * | 2019-10-31 | 2020-02-18 | 合肥工业大学 | Generation method and system based on wind power/photovoltaic classical scene set |
| CN111934319A (en) * | 2020-08-14 | 2020-11-13 | 合肥工业大学 | Generation method and system based on wind power typical scene set |
| CN112653198A (en) * | 2020-12-17 | 2021-04-13 | 山东大学 | Wind power output scene generation method and system based on prediction box |
-
2023
- 2023-08-09 CN CN202310995610.9A patent/CN116720448B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004086896A (en) * | 2002-08-06 | 2004-03-18 | Fuji Electric Holdings Co Ltd | Method and system for constructing adaptive prediction model |
| CN103259285A (en) * | 2013-05-03 | 2013-08-21 | 国家电网公司 | Method for optimizing short running of electric power system comprising large-scale wind power |
| CN103955779A (en) * | 2014-05-23 | 2014-07-30 | 武汉大学 | Wind power climbing event probability scene prediction method |
| CN107944640A (en) * | 2017-12-18 | 2018-04-20 | 国网山东省电力公司经济技术研究院 | A kind of regenerative resource portfolio optimization optimisation technique method and device |
| CN109816149A (en) * | 2018-12-28 | 2019-05-28 | 中国电力科学研究院有限公司 | A kind of wind power plant is contributed scene generating method and device at random |
| CN110807554A (en) * | 2019-10-31 | 2020-02-18 | 合肥工业大学 | Generation method and system based on wind power/photovoltaic classical scene set |
| CN111934319A (en) * | 2020-08-14 | 2020-11-13 | 合肥工业大学 | Generation method and system based on wind power typical scene set |
| CN112653198A (en) * | 2020-12-17 | 2021-04-13 | 山东大学 | Wind power output scene generation method and system based on prediction box |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116720448A (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Probabilistic forecast for multiple wind farms based on regular vine copulas | |
| Cervone et al. | Short-term photovoltaic power forecasting using Artificial Neural Networks and an Analog Ensemble | |
| Abuella et al. | Random forest ensemble of support vector regression models for solar power forecasting | |
| CN116720448B (en) | Wind power generation random simulation method, device, equipment and medium | |
| Lezama et al. | A new hybrid-adaptive differential evolution for a smart grid application under uncertainty | |
| Zhang et al. | Stochastic model predictive control using a combination of randomized and robust optimization | |
| CN111339066B (en) | Database optimization method and device, electronic equipment and computer-readable storage medium | |
| Scholz et al. | A cyclic time-dependent Markov process to model daily patterns in wind turbine power production | |
| CN106529700B (en) | Wind power plant prediction model construction method and system based on space-time correlation | |
| CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
| CN115688547A (en) | Simulated weather scenarios and extreme weather predictions | |
| CN115239105A (en) | Method and device for evaluating wind resources of in-service wind power plant | |
| CN114648156A (en) | Time series load prediction method based on convolutional neural network | |
| CN111950752A (en) | Photovoltaic power station generating capacity prediction method, device and system and storage medium thereof | |
| CN116523145B (en) | Photovoltaic power ultra-short-term prediction method and device, computer equipment and storage medium | |
| Yan et al. | Grid integration of wind generation considering remote wind farms: Hybrid Markovian and interval unit commitment | |
| CN117406309A (en) | Multi-numerical value calculation member generation method, device and storage medium | |
| CN109840308B (en) | Regional wind power probability forecasting method and system | |
| CN115392101A (en) | Method and system for generating comprehensive energy random scene | |
| Yang et al. | Probabilistic modeling of renewable energy source based on Spark platform with large‐scale sample data | |
| Sulaeman et al. | Evaluation of wind capacity credit using discrete convolution considering the mechanical failure of wind turbines | |
| Bacu et al. | Calibration of SWAT hydrological models in a distributed environment using the gSWAT application | |
| Elkantassi et al. | INFERENCE AND SENSITIVITY IN STOCHASTIC WIND POWER FORECAST MODELS. | |
| Ryazanova et al. | Integration of modern statistical tools for the analysis of climate extremes into the web-GIS “CLIMATE” | |
| CN117220286B (en) | Risk assessment method, device and medium for water-wind-solar multi-energy complementary system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |